Kerry Back
BUSI 520, Fall 2022
JGSB, Rice University
If \(w_i>0\) and \(b<0\), then \(y>0\) only when \(x_i\) are large enough.
A neuron fires when it is sufficiently stimulated by signals from other neurons (in prior layer).
For regression problems, the output function is linear
\[ y = b+w_1x_1 + \cdots + w_nx_n\].
For classification, there is a linear function for each class and the output is the set of probabilities \(e^{y_i}/\sum e^{y_j}\).